Paolo Brenner: raw computed results
The raw ranking from the production similarity calculation (face-embedding centroid cosine → gender-cohort z-normalization). The web-opinion crown, curation, and fusion re-rank are removed.
- 1
62.3%z 3.82 - 2
56.5%z 3.76 - 3
51.9%z 3.71 - 4
47.7%z 3.64 - 5
46.8%z 3.59 - 6
46.7%z 3.58 - 7
45.5%z 3.50 - 8
45.4%z 3.50 - 9
45.1%z 3.48 - 10
44.9%z 3.46 - 11
42.5%z 3.31 - 12
41%z 3.21 - 13
40.5%z 3.18 - 14
40.4%z 3.17 - 15
40.2%z 3.16 - 16
40.1%z 3.16 - 17
40%z 3.15 - 18
39.9%z 3.14 - 19
39.6%z 3.12 - 20
39.2%z 3.09 - 21
38.6%z 3.05 - 22
38.5%z 3.05 - 23
38.5%z 3.05 - 24
38.3%z 3.04 - 25
37.7%z 3.00 - 26
37.7%z 3.00 - 27
37.4%z 2.98 - 28
37.1%z 2.96 - 29
37.1%z 2.96 - 30
37%z 2.95 - 31
36.5%z 2.92 - 32
36.4%z 2.92 - 33
36.4%z 2.92 - 34
35.9%z 2.88 - 35
35.8%z 2.88 - 36
35.4%z 2.85 - 37
35.3%z 2.84 - 38
34.9%z 2.82 - 39
34.8%z 2.81 - 40
34.5%z 2.79 - 41
34.5%z 2.79 - 42
34.3%z 2.78 - 43
34.3%z 2.78 - 44
34.3%z 2.78 - 45
34.2%z 2.77 - 46
34.2%z 2.77 - 47
34.1%z 2.77 - 48
34.1%z 2.77 - 49
34.1%z 2.76 - 50
34%z 2.76